import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler, StandardScaler
#import seaborn as sns
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.metrics import classification_report, accuracy_score

from sklearn.ensemble import RandomForestClassifier

jupyter nbconvert --to html "churn_Modelling assignment.ipynb"

  Cell In[1], line 1
    jupyter nbconvert --to html "churn_Modelling assignment.ipynb"
            ^
SyntaxError: invalid syntax

import matplotlib
matplotlib.use('TkAgg')  
import matplotlib.pyplot as plt

#load dataset
df = pd.read_csv('promotion_dataset.csv')
df.head()

	EmployeeNo	Division	Qualification	Gender	Channel_of_Recruitment	Trainings_Attended	Year_of_birth	Last_performance_score	Year_of_recruitment	Targets_met	Previous_Award	Training_score_average	State_Of_Origin	Foreign_schooled	Marital_Status	Past_Disciplinary_Action	Previous_IntraDepartmental_Movement	No_of_previous_employers	Promoted_or_Not
0	YAK/S/00001	Commercial Sales and Marketing	MSc MBA and PhD	Female	Direct Internal process	2	1986	12.5	2011	1	0	41	ANAMBRA	No	Married	No	No	0	0
1	YAK/S/00002	Customer Support and Field Operations	First Degree or HND	Male	Agency and others	2	1991	12.5	2015	0	0	52	ANAMBRA	Yes	Married	No	No	0	0
2	YAK/S/00003	Commercial Sales and Marketing	First Degree or HND	Male	Direct Internal process	2	1987	7.5	2012	0	0	42	KATSINA	Yes	Married	No	No	0	0
3	YAK/S/00004	Commercial Sales and Marketing	First Degree or HND	Male	Agency and others	3	1982	2.5	2009	0	0	42	NIGER	Yes	Single	No	No	1	0
4	YAK/S/00006	Information and Strategy	First Degree or HND	Male	Direct Internal process	3	1990	7.5	2012	0	0	77	AKWA IBOM	Yes	Married	No	No	1	0

# getting information about dataset
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 38312 entries, 0 to 38311
Data columns (total 19 columns):
 #   Column                               Non-Null Count  Dtype  
---  ------                               --------------  -----  
 0   EmployeeNo                           38312 non-null  object 
 1   Division                             38312 non-null  object 
 2   Qualification                        36633 non-null  object 
 3   Gender                               38312 non-null  object 
 4   Channel_of_Recruitment               38312 non-null  object 
 5   Trainings_Attended                   38312 non-null  int64  
 6   Year_of_birth                        38312 non-null  int64  
 7   Last_performance_score               38312 non-null  float64
 8   Year_of_recruitment                  38312 non-null  int64  
 9   Targets_met                          38312 non-null  int64  
 10  Previous_Award                       38312 non-null  int64  
 11  Training_score_average               38312 non-null  int64  
 12  State_Of_Origin                      38312 non-null  object 
 13  Foreign_schooled                     38312 non-null  object 
 14  Marital_Status                       38312 non-null  object 
 15  Past_Disciplinary_Action             38312 non-null  object 
 16  Previous_IntraDepartmental_Movement  38312 non-null  object 
 17  No_of_previous_employers             38312 non-null  int64  
 18  Promoted_or_Not                      38312 non-null  int64  
dtypes: float64(1), int64(8), object(10)
memory usage: 5.6+ MB

# more info on rows and collumns
df.shape

(38312, 19)

#information about missing data
round((df.isnull().sum() / df.shape[0]) * 100, 2)

EmployeeNo                             0.00
Division                               0.00
Qualification                          4.38
Gender                                 0.00
Channel_of_Recruitment                 0.00
Trainings_Attended                     0.00
Year_of_birth                          0.00
Last_performance_score                 0.00
Year_of_recruitment                    0.00
Targets_met                            0.00
Previous_Award                         0.00
Training_score_average                 0.00
State_Of_Origin                        0.00
Foreign_schooled                       0.00
Marital_Status                         0.00
Past_Disciplinary_Action               0.00
Previous_IntraDepartmental_Movement    0.00
No_of_previous_employers               0.00
Promoted_or_Not                        0.00
dtype: float64

# handling missing data by filling with mode
df['Qualification'] = df['Qualification'].fillna(df['Qualification'].mode()[0])

#crosscheck missing data filled
round((df.isnull().sum() / df.shape[0]) * 100, 2)

EmployeeNo                             0.0
Division                               0.0
Qualification                          0.0
Gender                                 0.0
Channel_of_Recruitment                 0.0
Trainings_Attended                     0.0
Year_of_birth                          0.0
Last_performance_score                 0.0
Year_of_recruitment                    0.0
Targets_met                            0.0
Previous_Award                         0.0
Training_score_average                 0.0
State_Of_Origin                        0.0
Foreign_schooled                       0.0
Marital_Status                         0.0
Past_Disciplinary_Action               0.0
Previous_IntraDepartmental_Movement    0.0
No_of_previous_employers               0.0
Promoted_or_Not                        0.0
dtype: float64

# identify collumn data types
cat_col = [col for col in df.columns if df[col].dtype == 'object']
num_col = [col for col in df.columns if df[col].dtype != 'object']

print('Categorical columns:', cat_col)
print('Numerical columns:', num_col)

Categorical columns: ['EmployeeNo', 'Division', 'Qualification', 'Gender', 'Channel_of_Recruitment', 'State_Of_Origin', 'Foreign_schooled', 'Marital_Status', 'Past_Disciplinary_Action', 'Previous_IntraDepartmental_Movement']
Numerical columns: ['Trainings_Attended', 'Year_of_birth', 'Last_performance_score', 'Year_of_recruitment', 'Targets_met', 'Previous_Award', 'Training_score_average', 'No_of_previous_employers', 'Promoted_or_Not']

#count unique data for categorical data types
df[cat_col].nunique()

EmployeeNo                             38312
Division                                   9
Qualification                              3
Gender                                     2
Channel_of_Recruitment                     3
State_Of_Origin                           37
Foreign_schooled                           2
Marital_Status                             3
Past_Disciplinary_Action                   2
Previous_IntraDepartmental_Movement        2
dtype: int64

#statistical summary of dataset
df.describe()

	Trainings_Attended	Year_of_birth	Last_performance_score	Year_of_recruitment	Targets_met	Previous_Award	Training_score_average	No_of_previous_employers	Promoted_or_Not
count	38312.000000	38312.000000	38312.000000	38312.000000	38312.000000	38312.000000	38312.000000	38312.000000	38312.000000
mean	2.253680	1986.209334	7.698959	2013.139695	0.352996	0.023152	55.366465	1.040953	0.084595
std	0.609443	7.646047	3.744135	4.261451	0.477908	0.150388	13.362741	1.235738	0.278282
min	2.000000	1950.000000	0.000000	1982.000000	0.000000	0.000000	31.000000	0.000000	0.000000
25%	2.000000	1982.000000	5.000000	2012.000000	0.000000	0.000000	43.000000	0.000000	0.000000
50%	2.000000	1988.000000	7.500000	2014.000000	0.000000	0.000000	52.000000	1.000000	0.000000
75%	2.000000	1992.000000	10.000000	2016.000000	1.000000	0.000000	68.000000	1.000000	0.000000
max	11.000000	2001.000000	12.500000	2018.000000	1.000000	1.000000	91.000000	6.000000	1.000000

# generate profiling report 
from ydata_profiling import ProfileReport
df.profile_report()

Upgrade to ydata-sdk

Improve your data and profiling with ydata-sdk, featuring data quality scoring, redundancy detection, outlier identification, text validation, and synthetic data generation.

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

100%|██████████| 19/19 [00:00<00:00, 27.90it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]

#correlation analysis
df.corr(numeric_only=True)

	Trainings_Attended	Year_of_birth	Last_performance_score	Year_of_recruitment	Targets_met	Previous_Award	Training_score_average	No_of_previous_employers	Promoted_or_Not
Trainings_Attended	1.000000	0.078710	-0.062042	0.056215	-0.044789	-0.007409	0.041065	0.000796	-0.024345
Year_of_birth	0.078710	1.000000	-0.175572	0.654666	0.025337	0.013627	0.048390	-0.003117	0.017991
Last_performance_score	-0.062042	-0.175572	1.000000	-0.190333	0.276350	0.026587	0.057836	-0.005428	0.119690
Year_of_recruitment	0.056215	0.654666	-0.190333	1.000000	0.076910	0.041995	0.037477	-0.003550	0.012287
Targets_met	-0.044789	0.025337	0.276350	0.076910	1.000000	0.092934	0.077201	-0.003308	0.224518
Previous_Award	-0.007409	0.013627	0.026587	0.041995	0.092934	1.000000	0.072360	0.003887	0.201434
Training_score_average	0.041065	0.048390	0.057836	0.037477	0.077201	0.072360	1.000000	0.008194	0.178448
No_of_previous_employers	0.000796	-0.003117	-0.005428	-0.003550	-0.003308	0.003887	0.008194	1.000000	0.001690
Promoted_or_Not	-0.024345	0.017991	0.119690	0.012287	0.224518	0.201434	0.178448	0.001690	1.000000

sns.countplot(x='Promoted_or_Not', data=df, hue='Promoted_or_Not', palette='Set1')
plt.title('promotion distribution')
plt.show()

C:\Users\HP\AppData\Local\Temp\ipykernel_8608\2511900159.py:3: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown
  plt.show()

plt.boxplot(df['Training_score_average'], vert=False)
plt.ylabel('Variable')
plt.xlabel('Targets_met')
plt.title('Box Plot')
plt.show()

C:\Users\HP\AppData\Local\Temp\ipykernel_8608\3987866815.py:5: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown
  plt.show()

plt.boxplot(df['Last_performance_score'], vert=False)
plt.ylabel('Variable')
plt.xlabel('Last_performance_score')
plt.title('Box Plot')
plt.show()

C:\Users\HP\AppData\Local\Temp\ipykernel_8608\3335382509.py:5: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown
  plt.show()

plt.boxplot(df['Year_of_recruitment'], vert=False)
plt.ylabel('Variable')
plt.xlabel('Year_of_recruitment')
plt.title('corr Plot in search of outliers')
plt.show()

C:\Users\HP\AppData\Local\Temp\ipykernel_8608\3332865500.py:5: UserWarning: FigureCanvasAgg is non-interactive, and thus cannot be shown
  plt.show()

# feature engineering - creating new feature 'Age' from 'Year_of_birth' to drop redundant data
df["Age"] = 2025 - df["Year_of_birth"]
df.head()

	EmployeeNo	Division	Qualification	Gender	Channel_of_Recruitment	Trainings_Attended	Year_of_birth	Last_performance_score	Year_of_recruitment	Targets_met	Previous_Award	Training_score_average	State_Of_Origin	Foreign_schooled	Marital_Status	Past_Disciplinary_Action	Previous_IntraDepartmental_Movement	No_of_previous_employers	Promoted_or_Not	Age
0	YAK/S/00001	Commercial Sales and Marketing	MSc MBA and PhD	Female	Direct Internal process	2	1986	12.5	2011	1	0	41	ANAMBRA	No	Married	No	No	0	0	39
1	YAK/S/00002	Customer Support and Field Operations	First Degree or HND	Male	Agency and others	2	1991	12.5	2015	0	0	52	ANAMBRA	Yes	Married	No	No	0	0	34
2	YAK/S/00003	Commercial Sales and Marketing	First Degree or HND	Male	Direct Internal process	2	1987	7.5	2012	0	0	42	KATSINA	Yes	Married	No	No	0	0	38
3	YAK/S/00004	Commercial Sales and Marketing	First Degree or HND	Male	Agency and others	3	1982	2.5	2009	0	0	42	NIGER	Yes	Single	No	No	1	0	43
4	YAK/S/00006	Information and Strategy	First Degree or HND	Male	Direct Internal process	3	1990	7.5	2012	0	0	77	AKWA IBOM	Yes	Married	No	No	1	0	35

#separating features and target variable
X = df[['Division', 'Qualification', 'Gender', 'Channel_of_Recruitment','Age', 'Trainings_Attended', 'Last_performance_score', 'Year_of_recruitment', 'Targets_met', 'Previous_Award', 'Training_score_average', 'Foreign_schooled', 'Past_Disciplinary_Action', 'Previous_IntraDepartmental_Movement', 'No_of_previous_employers']]
Y = df['Promoted_or_Not']

# scaling numerical features
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder

x1 = X.copy()

scaler = MinMaxScaler(feature_range=(0, 1))

num_col_ = [col for col in X.columns if X[col].dtype != 'object']

num_cols = x1.select_dtypes(include=['int64', 'float64']).columns
x1[num_col_] = scaler.fit_transform(x1[num_col_])

# encoding categorical features
cat_cols = x1.select_dtypes(include=['object']).columns
le = LabelEncoder()
for col in cat_cols:
    x1[col] = le.fit_transform(x1[col])
x1.head()

	Division	Qualification	Gender	Channel_of_Recruitment	Age	Trainings_Attended	Last_performance_score	Year_of_recruitment	Targets_met	Previous_Award	Training_score_average	Foreign_schooled	Past_Disciplinary_Action	Previous_IntraDepartmental_Movement	No_of_previous_employers
0	1	1	0	1	0.294118	0.000000	1.0	0.805556	1.0	0.0	0.166667	0	0	0	0.000000
1	2	0	1	0	0.196078	0.000000	1.0	0.916667	0.0	0.0	0.350000	1	0	0	0.000000
2	1	0	1	1	0.274510	0.000000	0.6	0.833333	0.0	0.0	0.183333	1	0	0	0.000000
3	1	0	1	0	0.372549	0.111111	0.2	0.750000	0.0	0.0	0.183333	1	0	0	0.166667
4	4	0	1	1	0.215686	0.111111	0.6	0.833333	0.0	0.0	0.766667	1	0	0	0.166667

# standardizing numerical features
scaler = StandardScaler()
X_standardized = scaler.fit_transform(x1)
print(X_standardized[:5])

[[-0.83158796  1.41479513 -1.53339317  0.99209997  0.02737841 -0.41625517
   1.28229978 -0.5021114   1.35384256 -0.15395043 -1.07512768 -3.24810652
  -0.06290405 -0.32218928 -0.84238477]
 [-0.41929682 -0.61751078  0.65214846 -0.86183301 -0.62656278 -0.41625517
   1.28229978  0.43654831 -0.73863832 -0.15395043 -0.25193251  0.30787168
  -0.06290405 -0.32218928 -0.84238477]
 [-0.83158796 -0.61751078  0.65214846  0.99209997 -0.10340983 -0.41625517
  -0.05313941 -0.26744648 -0.73863832 -0.15395043 -1.00029176  0.30787168
  -0.06290405 -0.32218928 -0.84238477]
 [-0.83158796 -0.61751078  0.65214846 -0.86183301  0.55053137  1.22460994
  -1.3885786  -0.97144126 -0.73863832 -0.15395043 -1.00029176  0.30787168
  -0.06290405 -0.32218928 -0.03314114]
 [ 0.40528546 -0.61751078  0.65214846  0.99209997 -0.49577454  1.22460994
  -0.05313941 -0.26744648 -0.73863832 -0.15395043  1.61896561  0.30787168
  -0.06290405 -0.32218928 -0.03314114]]

# preparing for train-test split
categorical_features_X = X.select_dtypes(include=['object']).columns.tolist()
numerical_features_X = X.select_dtypes(include=['int64', 'float64']).columns.tolist()

preprocessor = ColumnTransformer(
    transformers=[
        ("cat", OneHotEncoder(handle_unknown='ignore'), categorical_features_X),
        ("num", StandardScaler(), numerical_features_X)
    ]
)

# train-test split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.25, random_state=42)

# building random forest model
rf_model = Pipeline(steps=[
    ('preprocess', preprocessor),
    ('model', RandomForestClassifier(
        n_estimators=300,
        max_depth=None,
        random_state=42,
        class_weight='balanced'  # handle imbalanced classes
    ))
])
# Fit
rf_model.fit(X_train, Y_train)

Pipeline(steps=[('preprocess',
                 ColumnTransformer(transformers=[('cat',
                                                  OneHotEncoder(handle_unknown='ignore'),
                                                  ['Division', 'Qualification',
                                                   'Gender',
                                                   'Channel_of_Recruitment',
                                                   'Foreign_schooled',
                                                   'Past_Disciplinary_Action',
                                                   'Previous_IntraDepartmental_Movement']),
                                                 ('num', StandardScaler(),
                                                  ['Age', 'Trainings_Attended',
                                                   'Last_performance_score',
                                                   'Year_of_recruitment',
                                                   'Targets_met',
                                                   'Previous_Award',
                                                   'Training_score_average',
                                                   'No_of_previous_employers'])])),
                ('model',
                 RandomForestClassifier(class_weight='balanced',
                                        n_estimators=300, random_state=42))])

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

# accuracy and classification report
rf_model.fit(X_train, Y_train)

rf_preds = rf_model.predict(X_test)

print("\n=== RANDOM FOREST RESULTS ===")
print("Accuracy:", accuracy_score(Y_test, rf_preds))
print(classification_report(Y_test, rf_preds))

=== RANDOM FOREST RESULTS ===
Accuracy: 0.9323449571935686
              precision    recall  f1-score   support

           0       0.93      1.00      0.96      8768
           1       0.84      0.25      0.38       810

    accuracy                           0.93      9578
   macro avg       0.89      0.62      0.67      9578
weighted avg       0.93      0.93      0.91      9578

import xgboost
from xgboost import XGBClassifier

xgb_model = Pipeline(steps=[
    ("preprocess", preprocessor),
    ("model", XGBClassifier(
        n_estimators=350,
        learning_rate=0.1,
        max_depth=6,
        subsample=0.9,
        colsample_bytree=0.8,
        random_state=42,
        eval_metric="logloss"
    ))
])

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 1
----> 1 xgb_model = Pipeline(steps=[
      2     ("preprocess", preprocessor),
      3     ("model", XGBClassifier(
      4         n_estimators=350,
      5         learning_rate=0.1,
      6         max_depth=6,
      7         subsample=0.9,
      8         colsample_bytree=0.8,
      9         random_state=42,
     10         eval_metric="logloss"
     11     ))
     12 ])

NameError: name 'Pipeline' is not defined

import sys
print(sys.executable)

c:\Users\HP\AppData\Local\Python\pythoncore-3.14-64\python.exe

import sys
print(sys.executable)

c:\Users\HP\AppData\Local\Python\pythoncore-3.14-64\python.exe

!py -m pip install xgboost

Requirement already satisfied: xgboost in c:\users\hp\appdata\local\python\pythoncore-3.14-64\lib\site-packages (3.1.2)
Requirement already satisfied: numpy in c:\users\hp\appdata\local\python\pythoncore-3.14-64\lib\site-packages (from xgboost) (2.3.5)
Requirement already satisfied: scipy in c:\users\hp\appdata\local\python\pythoncore-3.14-64\lib\site-packages (from xgboost) (1.16.3)